• Facets (new session)
• Description
• Metadata
• Settings
  • Rule: ActivityStreamsMapasEquivalentb3sb3sifpdbprdf-labelfacetshttp://dbpedia.org/resource/inference/rules/dbpedia#http://dbpedia.org/resource/inference/rules/opencyc#http://dbpedia.org/resource/inference/rules/umbel#http://dbpedia.org/resource/inference/rules/yago#http://dbpedia.org/schema/property_rules#http://www.ontologyportal.org/inference/rules/SUMO#http://www.ontologyportal.org/inference/rules/WordNet#http://www.w3.org/2002/07/owl#ldpoplwebskos-transurn:det:rdf:labelvirtrdf-labelvirtrdf-urlNone
    
  • Inverse Functional Properties: Disabled (fastest) Apply to subjects only Apply to objects only Apply to both subjects and objects
  • "Same As": Disabled (fastest) Apply to subjects only Apply to objects only Apply to both subjects and objects (recommended) Apply to subjects, objects and predicates (not recommended on big datasets) Apply to predicates only (special use cases only)

About: Evolutionary acquisition of neural topologies     Goto   Sponge   NotDistinct   Permalink

An Entity of Type : yago:WikicatEvolutionaryAlgorithms, within Data Space : dbpedia.demo.openlinksw.com associated with source document(s)

Type: yago:WikicatArtificialNeuralNetworksanatomical structureyago:Abstraction100002137yago:Act100030358yago:Activity100407535yago:Algorithm105847438yago:Communication100033020yago:ComputerArchitecture106725249yago:Description106724763yago:Event100029378yago:Message106598915yago:NeuralNetwork106725467yago:Procedure101023820yago:PsychologicalFeature100023100yago:YagoPermanentlyLocatedEntityyago:Rule105846932yago:Specification106725067yago:Statement106722453yago:WikicatEvolutionaryAlgorithms New Facet based on Instances of this Class

Evolutionary acquisition of neural topologies (EANT/EANT2) is an evolutionary reinforcement learning method that evolves both the topology and weights of artificial neural networks. It is closely related to the works of Angeline et al. and Stanley and Miikkulainen. Like the work of Angeline et al., the method uses a type of parametric mutation that comes from evolution strategies and evolutionary programming (now using the most advanced form of the evolution strategies CMA-ES in EANT2), in which adaptive step sizes are used for optimizing the weights of the neural networks. Similar to the work of Stanley (NEAT), the method starts with minimal structures which gain complexity along the evolution path.